Can CodeGeeX 4 9B run on Radeon PRO W7900 DS 48GB?

YES — Runs Great

A75Great

○Estimated from fit model

CodeGeeX 4 9B needs ~11.8 GB VRAM. Radeon PRO W7900 DS 48GB has 48.0 GB. With Q4_K_M quantization, expect ~102 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 11.8 GB, 101.6 tok/s, Runs well

11.8 GB required48.0 GB available

25% VRAM used

Fit status

Runs well

Decode

101.6 tok/s

TTFT

1906 ms

Safe context

131K

Memory

11.8 GB / 48.0 GB

Memory breakdown

Weights5.5 GB

KV Cache0.6 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsCodeGeeX 4 9B on Radeon PRO W7900 DS 48GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
 """Sort a list using the quicksort algorithm.

 Args:
 arr: List of integers to sort.

 Returns:
 A new sorted list.
 """
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 101.6 tok/s decode · 1.9s TTFT (warm) · 254 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	101.6 tok/s	1040 ms	131K
Coding	A	Runs well	101.6 tok/s	1906 ms	131K
Agentic Coding	A	Runs well	101.6 tok/s	2773 ms	131K
Reasoning	A	Runs well	101.6 tok/s	2253 ms	131K
RAG	A	Runs well	101.6 tok/s	3466 ms	131K

Quantization options

How CodeGeeX 4 9B (9B params) fits at each quantization level on Radeon PRO W7900 DS 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.5 GB	Low	B69
Q3_K_S	3	4.4 GB	Low	B69
NVFP4	4	5.0 GB	Medium	B70
Q4_K_M	4	5.5 GB	Medium	B70
Q5_K_M	5	6.5 GB	High	B70
Q6_K	6	7.4 GB	High	B70
Q8_0	8	9.6 GB	Very High	A71
F16Best for your GPU	16	18.5 GB	Maximum	A73

Get started

Copy-paste commands to run CodeGeeX 4 9B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "THUDM/codegeex4-all-9b" \
 --hf-file "codegeex4-all-9b-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your Radeon PRO W7900 DS 48GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	77.1 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	33.4 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	23.9 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	64.8 tok/s
👁 Alibaba Qwen3-VL 30B A3B Instruct	30B	S	79.7 tok/s

Frequently asked questions

See all results for Radeon PRO W7900 DS 48GB See all hardware for CodeGeeX 4 9B

URL: https://willitrunai.com/can-run/codegeex-4-9b-on-radeon-pro-w7900-ds-48gb

⇱ CodeGeeX 4 9B on Radeon PRO W7900 DS 48GB? YES